Geographic information dynamic early warning deployment and control method

Abstract

The invention discloses a geographic information dynamic early-warning deployment and control method, and particularly relates to the technical field of geographic information early-warning deployment and control. Rainfall data in a cruising area of a target unmanned aerial vehicle is acquired, the rainfall data is analyzed, the cruising frequency of the unmanned aerial vehicle is flexibly adjusted, and when the cruising frequency of the target unmanned aerial vehicle is increased, the target unmanned aerial vehicle is monitored. Monitoring the running state of the target unmanned aerial vehicle and the rainfall degree of the cruise area, comprehensively analyzing the running state of the target unmanned aerial vehicle and the rainfall degree of the cruise area, and sending out an early warning signal when the target unmanned aerial vehicle has a running hidden danger; a standby unmanned aerial vehicle screening model is constructed based on a multi-criterion decision analysis method to match an optimal standby unmanned aerial vehicle, a target unmanned aerial vehicle is replaced, continuity and stability of a monitoring task are ensured, and accuracy of the standby unmanned aerial vehicle screening model is verified by performing stability analysis on geographic information data transmitted by the standby unmanned aerial vehicle. Continuous monitoring of the lake area is improved, and potential breach risks are found and processed in time.

Description

Technical Field

[0001] The present invention relates to the technical field of geographic information early warning and control, and more specifically, to a geographic information dynamic early warning and control method. Background Art

[0002] A geographic information dynamic early warning and control method refers to a technology that uses geographic information systems and real-time data analysis technology to conduct real-time monitoring and early warning of potential natural disasters, emergencies or safety hazards. In the prevention of breach risks of large lakes, the use of geographic information systems and real-time data analysis technology for dynamic early warning and control can significantly improve the monitoring and response capabilities of potential breach risks. The lake water level, dam conditions and surrounding environment are monitored by deploying drone groups, and the monitoring data is transmitted to the geographic information system and combined with real-time data analysis technology to predict potential breach risks.

[0003] When there is a risk of lake breaching, it is usually accompanied by heavy rain. In the face of heavy rain, increasing the frequency of drone cruising is usually a necessary option. However, different individual drones in the drone swarm may have differences in their own performance and the degree of heavy rain in the cruising area. This may lead to the inability to complete continuous monitoring of lake water levels, dam conditions and surrounding environment when faced with a sudden increase in cruising demand.

[0004] In order to solve the above defects, a technical solution is now provided. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a geographic information dynamic early warning control method to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A geographic information dynamic early warning and control method comprises the following steps:

[0008] Step S1, obtaining rainfall data in the target UAV cruising area, analyzing the rainfall data, and determining whether to increase the cruising frequency of the target UAV;

[0009] Step S2, when the cruising frequency of the target UAV increases, monitor the operating status of the target UAV and the rainfall level in the cruising area, conduct a comprehensive analysis of the operating status of the target UAV and the rainfall level in the cruising area, determine whether the target UAV has any operating risks, and determine whether to issue an early warning signal;

[0010] Step S3: when the target UAV has an operational risk, a backup UAV screening model is constructed based on a multi-criteria decision analysis method to match the best backup UAV from the backup UAV group and replace the target UAV;

[0011] Step S4, performing stability analysis on the geographic information data transmitted by the backup UAV, and verifying the accuracy of the backup UAV screening model based on the analysis results.

[0012] In a preferred embodiment, the time series change of rainfall data is analyzed by moving average method to determine the change trend of rainfall intensity, as follows:

[0013] Determine a window size n, which represents the time window of the moving average, and calculate the moving average value ydp of rainfall according to the time window of the moving average i , the calculation expression is as follows In the formula, jy i-2 、jy i-1 、jy i They represent the i-2th, i-1th, and ith rainfall data in the rainfall data time series set, respectively, and i≥3;

[0014] The moving average of rainfall is compared with the rainfall intensity threshold. When the moving average of rainfall is greater than the rainfall intensity threshold, the cruising frequency of the target UAV is increased. When the moving average of rainfall is less than or equal to the rainfall intensity threshold, there is no need to increase the cruising frequency of the target UAV.

[0015] In a preferred embodiment, when the cruising frequency of the target UAV increases, the operating state of the target UAV and the rainfall degree in the cruising area are monitored, and the operating state information of the target UAV and the rainfall degree impact information in the cruising area are obtained;

[0016] The operating status information of the target UAV includes the cruise route deviation coefficient, power consumption rate coefficient, attitude control delay coefficient, and the rainfall degree impact information in the cruise area includes the raindrop impact force coefficient;

[0017] The cruise route deviation coefficient, power consumption rate coefficient, attitude control delay coefficient, and raindrop impact force coefficient are marked as xhl, dxh, zky, and ycx, respectively.

[0018] In a preferred embodiment, the logic for obtaining the cruise route deviation coefficient is as follows:

[0019] According to the built-in positioning system of the target UAV, the actual spatial coordinate point set of the target UAV when cruising in the cruising area is obtained, and the actual spatial coordinate point set is compared with the preset spatial coordinate point set of the pre-planned cruising path to calculate the cruising route deviation coefficient. The expression is as follows Where (x j ,y j ,z j ) represents the jth group of spatial coordinates in the actual spatial coordinate point set, Represents the jth group of spatial coordinates in the preset spatial coordinate point set, j={1, 2, 3...J}, and J is a positive integer.

[0020] In a preferred embodiment, the logic for obtaining the power consumption rate coefficient is as follows:

[0021] Preset a fixed time period, record the initial power and final power of the target drone's onboard battery at the initial and final moments of multiple fixed time periods, perform a difference calculation on the initial power and final power to obtain the power consumption, and calculate the power consumption rate coefficient. The expression is as follows: Where dx represents the power consumption, Δt represents the fixed time period, jsd represents the final power of the target UAV's onboard battery at the end of the fixed time period, and b represents the sequence number of the fixed time period, b = {1, 2, 3...B}, where B is a positive integer.

[0022] In a preferred embodiment, the logic for obtaining the attitude control delay coefficient is as follows:

[0023] Record the time when the attitude control system of the target UAV issues a flight attitude control command each time and the time when the target UAV actually adjusts its attitude, and perform a difference calculation between the time of issuance and the time of adjustment to obtain the response time each time;

[0024] Obtain the optimal response time range from when the attitude control system of the target UAV issues a flight attitude control command to when the target UAV actually performs attitude adjustment, and mark the optimal response time range as sx1-sx2;

[0025] Marking the response time greater than the optimal response time range as the response delay time;

[0026] Calculate the attitude control delay coefficient, the expression is as follows

[0027] In a preferred embodiment, the logic for obtaining the raindrop impact force coefficient is as follows:

[0028] The target UAV is equipped with a raindrop sensor to measure the size of raindrops in the cruising area, obtain multiple sets of measurement data, and calculate the average diameter of raindrops. The expression is as follows Where d f represents the measured diameter of the fth raindrop, f = {1, 2, 3…F}, F is a positive integer;

[0029] Calculate the raindrop mass MZ, the expression is as follows Where π represents pi, ρ represents water density;

[0030] Configure the Doppler radar on the target UAV to measure the speed ys of raindrops and calculate the kinetic energy of raindrops. The expression is as follows

[0031] Calculate the raindrop impact force FC, the expression is as follows Where csj represents the contact time between raindrops and the target UAV surface;

[0032] Calculate the raindrop impact coefficient, the expression is as follows Where MB represents the surface area of ​​the target UAV.

[0033] In a preferred embodiment, the cruise route deviation coefficient, the power consumption rate coefficient, the attitude control delay coefficient, and the raindrop impact force coefficient are normalized, and a target UAV operation hidden danger assessment model is constructed according to the normalized cruise route deviation coefficient, the power consumption rate coefficient, the attitude control delay coefficient, and the raindrop impact force coefficient to generate a target UAV operation hidden danger assessment index MBY. The model is based on the following formula: Wherein a1, a2, a3, and a4 represent the preset proportional coefficients of the cruise route deviation coefficient, the power consumption rate coefficient, the attitude control delay coefficient, and the raindrop impact force coefficient, respectively, and a1, a2, a3, and a4 are all greater than 0;

[0034] The target UAV operation hidden danger assessment index is compared with the preset target UAV operation hidden danger assessment index threshold, and the operation hidden dangers of the target UAV are classified as follows:

[0035] If the target UAV operation hazard assessment index is greater than the target UAV operation hazard assessment index threshold, it indicates that the target UAV has an operation hazard, and a warning signal is issued, indicating that the target UAV needs to be replaced;

[0036] If the target UAV operation hazard assessment index is less than or equal to the target UAV operation hazard assessment index threshold, there is no need to issue a warning signal.

[0037] In a preferred embodiment, in step S3, when the target UAV has an operational risk, a backup UAV screening model is constructed based on a multi-criteria decision analysis method as follows:

[0038] Step A1, determining various evaluation indicators for selecting backup drones;

[0039] The evaluation indicators for selecting backup drones include but are not limited to flight time, wind resistance level, rain resistance level, sensor accuracy, data transmission connection interruption rate, and mission success rate;

[0040] Step A2, constructing a decision matrix, normalizing the decision matrix, and constructing a weighted normalized matrix;

[0041] Step A3, determining the ideal solution and the negative ideal solution, and calculating the ideal solution distance and the negative ideal solution distance of each backup UAV by a formula;

[0042] Step A4, obtaining a backup UAV screening coefficient according to the ideal solution distance and the negative ideal solution distance of the backup UAV;

[0043] Step A5, sort the backup drones in the backup drone group from large to small according to the backup drone screening coefficient, complete the construction of the backup drone screening model, the output of the model is the backup drone with the first ranking, and the backup drone with the first ranking is used as the optimal backup drone to replace the target drone.

[0044] In a preferred embodiment, in step S4, the geographic information data transmitted by the backup drone is subjected to stability analysis, and the accuracy of the backup drone screening model is verified according to the analysis results, as follows:

[0045] Step B1, obtaining geographic information data transmitted by the backup UAV, for each geographic information data point p, calculating the distance between the geographic information data point p and other data points in the geographic information data set, and obtaining the H nearest neighboring points to the geographic information data point p;

[0046] Step B2, for geographic information data point p, calculate the average reachable distance to its h nearest neighboring points, and calculate the local reachable density of geographic information data point p;

[0047] Step B3, calculate the local outlier factor, count the number of times the local outlier factor is greater than the local outlier factor threshold, compare the number of times the local outlier factor is greater than the local outlier factor threshold with the number threshold, verify the accuracy of the backup UAV screening model, if the number of times the local outlier factor is greater than the local outlier factor threshold is greater than the number threshold, then generate an accuracy abnormality signal; if the number of times the local outlier factor is greater than the local outlier factor threshold is less than or equal to the number threshold, then generate an accuracy stability signal.

[0048] Technical effects and advantages of the present invention:

[0049] 1. The present invention obtains rainfall data in the cruising area of ​​the target UAV, analyzes the rainfall data, and flexibly adjusts the cruising frequency of the UAV. When the cruising frequency of the target UAV increases, the operating status of the target UAV and the rainfall degree in the cruising area are monitored, and a comprehensive analysis is performed on the operating status of the target UAV and the rainfall degree in the cruising area. When the target UAV has an operating hazard, an early warning signal is issued, and a backup UAV screening model is constructed based on a multi-criteria decision analysis method to match the optimal backup UAV from the backup UAV group, and the target UAV is replaced to ensure the continuity and stability of the monitoring task. The accuracy of the backup UAV screening model is verified by performing a stability analysis on the geographic information data transmitted by the backup UAV, thereby improving the reliability of the system. By increasing the cruising frequency and reasonably dispatching UAVs, continuous monitoring of the lake area is improved, and potential breach risks are discovered and handled in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0051] Figure 1 Schematic diagram of the structure of the method of the embodiment of the present invention. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] Example: Figure 1 The present invention provides a method for dynamic early warning and control of geographic information, comprising the following steps:

[0054] Step S1, obtaining rainfall data in the target UAV cruising area, analyzing the rainfall data, and determining whether to increase the cruising frequency of the target UAV;

[0055] The target drone is any drone in the drone swarm used to monitor the lake water level, dam conditions and surrounding environment;

[0056] By equipping the target UAV with a rainfall sensor (such as a rain gauge) and a weather radar, and obtaining the rainfall data in the target UAV's cruising area from the ground meteorological station in real time, and transmitting the obtained rainfall data to the central control unit through wireless or wired transmission technology, the central control unit performs data preprocessing on the received rainfall data, including missing value and outlier processing, etc.; the preprocessed rainfall data is integrated in time and space to form a unified time series set of rainfall data;

[0057] It should be noted that each data in the rainfall data time series set is rainfall data from a fixed time, and the fixed time can be set according to the actual situation, for example, five minutes, ten minutes, twenty minutes, etc.;

[0058] The time series changes of rainfall data are analyzed by moving average method to determine the changing trend of rainfall intensity, as follows:

[0059] Determine a window size n, which represents the time window of the moving average, and calculate the moving average value ydp of rainfall according to the time window of the moving average i , the calculation expression is as follows In the formula, jy i-2 ,hy i-1 、jy i They represent the i-2th, i-1th, and ith rainfall data in the rainfall data time series set, respectively, and i≥3;

[0060] The moving average of rainfall is compared with the rainfall intensity threshold. When the moving average of rainfall is greater than the rainfall intensity threshold, it indicates that the rainfall in the target drone cruising area continues to increase, and the target drone's cruising frequency needs to be increased. When the moving average of rainfall is less than or equal to the rainfall intensity threshold, it indicates that the rainfall in the target drone cruising area is small, and the pre-planned drone cruising plan can meet the monitoring needs of the lake water level, dam conditions and surrounding environment, and there is no need to increase the target drone's cruising frequency.

[0061] It should be noted that the rainfall intensity threshold can be determined by those skilled in the art based on historical data, meteorological standards, geographical location and environmental characteristics, and will not be elaborated herein;

[0062] Step S2, when the cruising frequency of the target UAV increases, monitor the operating status of the target UAV and the rainfall level in the cruising area, conduct a comprehensive analysis of the operating status of the target UAV and the rainfall level in the cruising area, determine whether the target UAV has any operating risks, and determine whether to issue an early warning signal;

[0063] When the cruising frequency of the target UAV increases, the operating status of the target UAV and the rainfall level in the cruising area are monitored, and the operating status information of the target UAV and the impact information of the rainfall level in the cruising area are obtained;

[0064] The operating status information of the target UAV includes the cruise route deviation coefficient, power consumption rate coefficient, attitude control delay coefficient, and the rainfall degree impact information in the cruise area includes the raindrop impact force coefficient;

[0065] The cruise route deviation coefficient, power consumption rate coefficient, attitude control delay coefficient, and raindrop impact force coefficient are marked as xhl, dxh, zky, and ycx respectively;

[0066] The cruise route deviation coefficient refers to the degree of deviation between the actual cruise route of the target UAV and the preset cruise route after the cruise frequency is increased. The larger the cruise route deviation coefficient, the more unstable the target UAV's operating state is, and the greater the probability of its operating hidden dangers. It may not be able to cope with the increased cruise demand in the next period of time. The smaller the cruise route deviation coefficient, the more stable the target UAV's operating state is, and the smaller the probability of its operating hidden dangers is.

[0067] The logic for obtaining the cruise route deviation coefficient is as follows:

[0068] According to the built-in positioning system of the target UAV, the actual spatial coordinate point set of the target UAV when cruising in the cruising area is obtained, and the actual spatial coordinate point set is compared with the preset spatial coordinate point set of the pre-planned cruising path to calculate the cruising route deviation coefficient. The expression is as follows Where (x j ,y j ,z j ) represents the jth group of spatial coordinates in the actual spatial coordinate point set, represents the jth group of spatial coordinates in the preset spatial coordinate point set, j = {1, 2, 3...J}, J is a positive integer;

[0069] The power consumption rate coefficient is used to measure the ratio of the target drone's onboard battery power consumption rate to the remaining power. When the power consumption rate coefficient is abnormally high, it indicates that the target drone's onboard battery may have potential risks, thereby increasing the target drone's operational risks. This indicator can help evaluate the target drone's onboard battery usage during mission execution. A smaller power consumption rate coefficient indicates a lower probability of a target drone's onboard battery having potential risks.

[0070] The logic for obtaining the power consumption rate coefficient is as follows:

[0071] Preset a fixed time period, record the initial power and final power of the target drone's onboard battery at the initial and final moments of multiple fixed time periods, perform a difference calculation on the initial power and final power to obtain the power consumption, and calculate the power consumption rate coefficient. The expression is as follows:

[0072] Where dx represents the power consumption, Δt represents the fixed time period, jsd represents the final power of the target UAV's onboard battery at the end of the fixed time period, and b represents the sequence number of the fixed time period, b = {1, 2, 3...B}, where B is a positive integer;

[0073] The attitude control delay coefficient is used to measure the response delay of the attitude control system to the flight attitude control of the target UAV every time the flight attitude is abnormal. This coefficient reflects the response speed and stability of the attitude control system of the target UAV. A larger attitude control delay coefficient indicates that the target UAV is more unstable in operation, and the probability of hidden dangers in operation is greater, and the probability of replacing the target UAV is greater. A smaller attitude control delay coefficient indicates that the target UAV is more stable in operation.

[0074] The logic for obtaining the attitude control delay coefficient is as follows:

[0075] Record the time when the attitude control system of the target UAV issues a flight attitude control command each time and the time when the target UAV actually adjusts its attitude, and perform a difference calculation between the time of issuance and the time of adjustment to obtain the response time each time;

[0076] Obtain the optimal response time range from when the attitude control system of the target UAV issues a flight attitude control command to when the target UAV actually performs attitude adjustment, and mark the optimal response time range as sx1-sx2;

[0077] It should be noted that the optimal response time range can be obtained by testing in an interference-free experimental environment, obtaining multiple groups of response time data, calculating the mean and standard deviation of the response time data, and performing a difference operation on the mean and standard deviation of the response time data to obtain the upper and lower limits of the optimal response time range;

[0078] Marking the response time greater than the optimal response time range as the response delay time;

[0079] Calculate the attitude control delay coefficient, the expression is as follows Where cyc represents the total number of flight attitude control commands issued by the attitude control system of the target UAV during the cruise of the target UAV, and ycc represents the total number of times the response time is marked as the response delay time;

[0080] The raindrop impact coefficient is used to measure the impact of the size of raindrops in the cruise area on the target UAV, reflecting the influence of the kinetic energy of raindrops on the structure and stability of the target UAV. The larger the raindrop impact coefficient, the greater the influence of the kinetic energy of raindrops in the cruise area on the structure and stability of the target UAV, and the greater the probability of its operation hidden dangers. Conversely, when the raindrop impact coefficient is smaller, it indicates that the kinetic energy of raindrops in the cruise area has a smaller impact on the structure and stability of the target UAV, and the probability of its operation hidden dangers is also smaller, and thus the probability of replacing the target UAV is smaller;

[0081] The logic for obtaining the raindrop impact coefficient is as follows:

[0082] The target UAV is equipped with a raindrop sensor to measure the size of raindrops in the cruising area, obtain multiple sets of measurement data, and calculate the average diameter of raindrops. The expression is as follows Where d f represents the measured diameter of the f-th raindrop, f = {1, 2, 3...F}, F is a positive integer;

[0083] Calculate the raindrop mass MZ, the expression is as follows Where π represents pi, ρ represents water density;

[0084] Configure the Doppler radar on the target UAV to measure the speed ys of raindrops and calculate the kinetic energy of raindrops. The expression is as follows

[0085] Calculate the raindrop impact force FC, the expression is as follows Where csj represents the contact time between raindrops and the target UAV surface;

[0086] Calculate the raindrop impact coefficient, the expression is as follows Where MB represents the surface area of ​​the target UAV;

[0087] The cruise route deviation coefficient, power consumption rate coefficient, attitude control delay coefficient, and raindrop impact force coefficient are normalized. According to the normalized cruise route deviation coefficient, power consumption rate coefficient, attitude control delay coefficient, and raindrop impact force coefficient, a target UAV operation hidden danger assessment model is constructed to generate the target UAV operation hidden danger assessment index MBY. The model is based on the following formula: Wherein a1, a2, a3, and a4 represent the preset proportional coefficients of the cruise route deviation coefficient, the power consumption rate coefficient, the attitude control delay coefficient, and the raindrop impact force coefficient, respectively, and a1, a2, a3, and a4 are all greater than 0;

[0088] It can be seen from the above calculation expression that the larger the cruise route deviation coefficient, the larger the power consumption rate coefficient, the larger the attitude control delay coefficient, and the larger the raindrop impact force coefficient, the larger the target UAV operation hidden danger assessment index, indicating that the target UAV's operation state is more unstable, the probability of its operation hidden danger is greater, and the probability of replacing the target UAV is greater. Conversely, the smaller the cruise route deviation coefficient, the smaller the power consumption rate coefficient, the smaller the attitude control delay coefficient, and the smaller the raindrop impact force coefficient, the smaller the target UAV operation hidden danger assessment index is, indicating that the target UAV's operation state is more stable, and the probability of its operation hidden danger is smaller;

[0089] The target UAV operation hidden danger assessment index is compared with the preset target UAV operation hidden danger assessment index threshold, and the operation hidden dangers of the target UAV are classified as follows:

[0090] If the target UAV operation hazard assessment index is greater than the target UAV operation hazard assessment index threshold, it indicates that the target UAV has an operation hazard, and a warning signal is issued, indicating that the target UAV needs to be replaced;

[0091] If the target UAV operation hidden danger assessment index is less than or equal to the target UAV operation hidden danger assessment index threshold, it indicates that the current target UAV can meet the increased cruising demand and there is no need to issue a warning signal;

[0092] Step S3: When the target UAV has an operational risk, a backup UAV screening model is constructed based on a multi-criteria decision analysis method to match the best backup UAV from the backup UAV group and replace the target UAV, as follows:

[0093] Step A1, determining various evaluation indicators for selecting backup drones;

[0094] The evaluation indicators for selecting backup drones include but are not limited to flight time, wind resistance level, rain resistance level, sensor accuracy, data transmission connection interruption rate, and mission success rate;

[0095] Endurance time refers to the maximum endurance time of the standby drone in the historical cruise record;

[0096] The wind resistance level refers to the maximum wind speed that the standby UAV can withstand in the historical cruise records, which is used as the quantitative value of the wind resistance level;

[0097] The rain resistance level refers to the maximum rainfall that the standby UAV can withstand in the historical cruise records, which is used as the quantitative value of the rain resistance level;

[0098] Sensor accuracy refers to the deviation between the sensor measurement value onboard the backup drone in the historical cruise record and the true value;

[0099] The data transmission connection interruption rate refers to the ratio of the number of connection interruptions during the data transmission process of the backup UAV in the historical cruise records to the cruise time;

[0100] It should be noted that the various evaluation indicators for screening backup drones are the various evaluation indicators used to construct a backup drone screening model;

[0101] Step A2, constructing a decision matrix, normalizing the decision matrix, and constructing a weighted normalized matrix;

[0102] Obtain the quantitative values ​​of various evaluation indicators of the backup drone, construct a decision matrix, and mark the decision matrix as where pz kg represents the g-th evaluation index of the k-th backup UAV, k = {1, 2, 3…K}, K is a positive integer, g = {1, 2, 3, 4, 5, 6};

[0103] Normalize the decision matrix to obtain the normalized decision matrix GZ. The normalization formula is as follows:

[0104] The expert empowerment method is adopted, that is, experts in this field are invited to determine the weights of various indicators through professional opinion surveys and comprehensive evaluations to ensure that the weight coefficients can accurately reflect the importance of various evaluation indicators for screening backup drones in the output of the backup drone screening model. In addition, various methods such as hierarchical analysis method and fuzzy comprehensive evaluation method can also be considered to determine the weight coefficients to ensure the objectivity and scientificity of the weight coefficients, which will not be elaborated here;

[0105] That is, we get the weighted normalized matrix QZ, whose weighted expression is as follows: kg =w g *gz kh ;

[0106] Step A3, determining the ideal solution and the negative ideal solution, and calculating the ideal solution distance and the negative ideal solution distance of each backup UAV by a formula;

[0107] The ideal solution is the maximum value combination of each indicator, and the ideal solution is marked as LX + , LX + =(min(qz k1 ), min(qz k2 ), ..., min(qz k6 ));

[0108] The negative ideal solution refers to the minimum combination of each indicator, and the negative ideal solution is marked as LX - , LX - =(min(qz k1 ), min(qzk2 ), ..., min(qz k6 ));

[0109] Calculate the ideal solution distance for backup drones

[0110] Calculate the negative ideal solution distance of the backup drone

[0111] Step A4, according to the ideal solution distance and negative ideal solution distance of the backup UAV, obtain the backup UAV screening coefficient, and the calculation expression for obtaining the backup UAV screening coefficient is as follows:

[0112] Step A5: sort the backup drones in the backup drone group from large to small according to the backup drone screening coefficient, and complete the construction of the backup drone screening model. The output of the model is the backup drone with the first ranking, and the backup drone with the first ranking is used as the optimal backup drone to replace the target drone.

[0113] It should be noted that step A1, step A2, step A3, step A4, and step A5 are the complete construction process of the backup drone screening model;

[0114] Step S4, performing stability analysis on the geographic information data transmitted by the backup drone, and verifying the accuracy of the backup drone screening model based on the analysis results, as follows:

[0115] Step B1, obtaining geographic information data transmitted by the backup UAV, for each geographic information data point p, calculating the distance between the geographic information data point p and other data points in the geographic information data set, and obtaining the H nearest neighboring points to the geographic information data point p;

[0116] For each geographic information data point p, calculate the distance dist(p, pt) between the geographic information data point p and other data points in the geographic information dataset. q ), the expression is as follows Where p v Represents the vth eigenvalue of geographic information data point p, pt qv represents the vth eigenvalue of the qth geographic information data point in the geographic information dataset;

[0117] Sort the distances between data points from small to large, filter out the distances between the first H data points, and obtain the H nearest neighboring points to the corresponding geographic information data point p;

[0118] It should be noted that H is a preset parameter, and a reference value is given by technicians in this field according to actual needs;

[0119] Step B2, for geographic information data point p, calculate the average reachable distance to its h nearest neighboring points, and calculate the local reachable density of geographic information data point p;

[0120] For a geographic information data point p, calculate its nearest neighbor point pl h The reachable distance is expressed as reach(p, pl h )=max(hdist h (pl h ), dist(p, pl h )), where hdist h (pl h ) represents geographic information data point pl h The distance to its hth nearest neighbor, dist(p, pl h ) represents the geographic information data point p to the geographic information data point pl h distance;

[0121] Calculate the average reachable distance avgreach, the expression is as follows h={1,2,3…H}, H is a positive integer;

[0122] Calculate the local reachability density lrd of geographic information data point p. The calculation expression is as follows

[0123] Step B3, calculating the local outlier factor, counting the number of times the local outlier factor is greater than the local outlier factor threshold, comparing the number of times the local outlier factor is greater than the local outlier factor threshold with the number threshold, and verifying the accuracy of the backup UAV screening model;

[0124] Calculate the local outlier factor, the expression is as follows Where lrd(p) represents the local reachability density of geographic information data point p, lrd(pl h ) represents the hth geographic information data point pl that is the nearest neighbor to the geographic information data point p h The local reachable density of

[0125] Compare the local outlier factor with the local outlier factor threshold, and count the number of times the local outlier factor is greater than the local outlier factor threshold;

[0126] The number of times the local outlier factor is greater than the local outlier factor threshold is compared with the number threshold, and the accuracy of the backup UAV screening model is verified. If the number of times the local outlier factor is greater than the local outlier factor threshold is greater than the number threshold, it indicates that the accuracy of the backup UAV screening model is low, and an abnormal accuracy signal is generated, and the model parameters need to be re-adjusted and optimized, for example, adding or replacing evaluation indicators, and adjusting the weight ratio corresponding to the evaluation indicators; if the number of times the local outlier factor is greater than the local outlier factor threshold is less than or equal to the number threshold, it indicates that the accuracy of the backup UAV screening model is high, which can effectively support the replacement decision of the UAV and generate a stable accuracy signal;

[0127] The present invention obtains rainfall data in the cruising area of ​​the target UAV, analyzes the rainfall data, and flexibly adjusts the cruising frequency of the UAV. When the cruising frequency of the target UAV increases, the operating status of the target UAV and the rainfall degree in the cruising area are monitored, and a comprehensive analysis is performed on the operating status of the target UAV and the rainfall degree in the cruising area. When the target UAV has an operating hazard, an early warning signal is issued, and a backup UAV screening model is constructed based on a multi-criteria decision analysis method to match the optimal backup UAV from the backup UAV group, and the target UAV is replaced to ensure the continuity and stability of the monitoring task. The accuracy of the backup UAV screening model is verified by performing a stability analysis on the geographic information data transmitted by the backup UAV, thereby improving the reliability of the system. By increasing the cruising frequency and reasonably dispatching UAVs, continuous monitoring of the lake area is improved, and potential breach risks are discovered and handled in a timely manner.

[0128] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0129] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0130] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for dynamic early warning and control of geographic information, characterized in that: The steps include: Step S1, obtaining rainfall data in the target UAV cruising area, analyzing the rainfall data, and determining whether to increase the cruising frequency of the target UAV; Step S2, when the cruising frequency of the target UAV increases, monitor the operating status of the target UAV and the rainfall level in the cruising area, conduct a comprehensive analysis of the operating status of the target UAV and the rainfall level in the cruising area, determine whether the target UAV has any operating risks, and determine whether to issue an early warning signal; Step S3: when the target UAV has an operational risk, a backup UAV screening model is constructed based on a multi-criteria decision analysis method to match the best backup UAV from the backup UAV group and replace the target UAV; Step S4, performing stability analysis on the geographic information data transmitted by the backup UAV, and verifying the accuracy of the backup UAV screening model based on the analysis results.

2. A geographic information dynamic early warning and control method according to claim 1, characterized in that: The time series changes of rainfall data are analyzed by moving average method to determine the changing trend of rainfall intensity, as follows: Determine a window size n, which represents the time window of the moving average, and calculate the moving average value ydp of rainfall according to the time window of the moving average i , the calculation expression is as follows In the formula, jy i-2 、jy i-1 、jy i They represent the i-2th, i-1th, and ith rainfall data in the rainfall data time series set, respectively, and i≥3; The moving average of rainfall is compared with the rainfall intensity threshold. When the moving average of rainfall is greater than the rainfall intensity threshold, the cruising frequency of the target UAV is increased. When the moving average of rainfall is less than or equal to the rainfall intensity threshold, there is no need to increase the cruising frequency of the target UAV.

3. A geographic information dynamic early warning and control method according to claim 2, characterized in that: When the cruising frequency of the target UAV increases, the operating status of the target UAV and the rainfall level in the cruising area are monitored, and the operating status information of the target UAV and the impact information of the rainfall level in the cruising area are obtained; The operating status information of the target UAV includes the cruise route deviation coefficient, power consumption rate coefficient, attitude control delay coefficient, and the rainfall degree impact information in the cruise area includes the raindrop impact force coefficient; The cruise route deviation coefficient, power consumption rate coefficient, attitude control delay coefficient, and raindrop impact force coefficient are marked as xhl, dxh, zky, and ycx, respectively.

4. A geographic information dynamic early warning and control method according to claim 3, characterized in that: The logic for obtaining the cruise route deviation coefficient is as follows: According to the built-in positioning system of the target UAV, the actual spatial coordinate point set of the target UAV when cruising in the cruising area is obtained, and the actual spatial coordinate point set is compared with the preset spatial coordinate point set of the pre-planned cruising path to calculate the cruising route deviation coefficient. The expression is as follows Where (x j ,y j ,z j ) represents the jth group of spatial coordinates in the actual spatial coordinate point set, Represents the jth group of spatial coordinates in the preset spatial coordinate point set, j={1, 2, 3...J}, and J is a positive integer.

5. A geographic information dynamic early warning and control method according to claim 4, characterized in that: The logic for obtaining the power consumption rate coefficient is as follows: Preset a fixed time period, record the initial power and final power of the target drone's onboard battery at the initial and final moments of multiple fixed time periods, perform a difference calculation on the initial power and final power to obtain the power consumption, and calculate the power consumption rate coefficient. The expression is as follows: Where dx represents the power consumption, Δt represents the fixed time period, jsd represents the final power of the target UAV's onboard battery at the end of the fixed time period, and b represents the sequence number of the fixed time period, b = {1, 2, 3...B}, where B is a positive integer.

6. A geographic information dynamic early warning and control method according to claim 5, characterized in that: The logic for obtaining the attitude control delay coefficient is as follows: Record the time when the attitude control system of the target UAV issues a flight attitude control command each time and the time when the target UAV actually adjusts its attitude, and perform a difference calculation between the issuance time and the adjustment time to obtain the response time each time; Obtain the optimal response time range from when the attitude control system of the target UAV issues a flight attitude control command to when the target UAV actually performs attitude adjustment, and mark the optimal response time range as sx1-sx2; Marking the response time greater than the optimal response time range as the response delay time; Calculate the attitude control delay coefficient, the expression is as follows 7. A geographic information dynamic early warning and control method according to claim 6, characterized in that: The logic for obtaining the raindrop impact coefficient is as follows: The target UAV is equipped with a raindrop sensor to measure the size of raindrops in the cruising area, obtain multiple sets of measurement data, and calculate the average diameter of raindrops. The expression is as follows Where d f represents the measured diameter of the f-th raindrop, f = {1, 2, 3...F}, F is a positive integer; Calculate the raindrop mass MZ, the expression is as follows Where π represents pi, ρ represents water density; Configure the Doppler radar on the target UAV to measure the speed ys of raindrops and calculate the kinetic energy of raindrops. The expression is as follows Calculate the raindrop impact force FC, the expression is as follows Where csj represents the contact time between raindrops and the target UAV surface; Calculate the raindrop impact coefficient, the expression is as follows Where MB represents the surface area of ​​the target UAV.

8. A geographic information dynamic early warning and control method according to claim 7, characterized in that: The cruise route deviation coefficient, power consumption rate coefficient, attitude control delay coefficient, and raindrop impact force coefficient are normalized. According to the normalized cruise route deviation coefficient, power consumption rate coefficient, attitude control delay coefficient, and raindrop impact force coefficient, a target UAV operation hidden danger assessment model is constructed to generate the target UAV operation hidden danger assessment index MBY. The model is based on the following formula: Wherein a1, a2, a3, and a4 represent the preset proportional coefficients of the cruise route deviation coefficient, the power consumption rate coefficient, the attitude control delay coefficient, and the raindrop impact force coefficient, respectively, and a1, a2, a3, and a4 are all greater than 0; The target UAV operation hidden danger assessment index is compared with the preset target UAV operation hidden danger assessment index threshold, and the operation hidden dangers of the target UAV are classified as follows: If the target UAV operation hazard assessment index is greater than the target UAV operation hazard assessment index threshold, it indicates that the target UAV has an operation hazard, and a warning signal is issued, indicating that the target UAV needs to be replaced; If the target UAV operation hazard assessment index is less than or equal to the target UAV operation hazard assessment index threshold, there is no need to issue a warning signal.

9. A geographic information dynamic early warning and control method according to claim 8, characterized in that: In step S3, when the target UAV has an operational risk, a backup UAV screening model is constructed based on the multi-criteria decision analysis method as follows: Step A1, determining various evaluation indicators for selecting backup drones; The evaluation indicators for selecting backup drones include but are not limited to flight time, wind resistance level, rain resistance level, sensor accuracy, data transmission connection interruption rate, and mission success rate; Step A2, constructing a decision matrix, normalizing the decision matrix, and constructing a weighted normalized matrix; Step A3, determining the ideal solution and the negative ideal solution, and calculating the ideal solution distance and the negative ideal solution distance of each backup UAV by a formula; Step A4, obtaining a backup UAV screening coefficient according to the ideal solution distance and the negative ideal solution distance of the backup UAV; Step A5, sort the backup drones in the backup drone group from large to small according to the backup drone screening coefficient, complete the construction of the backup drone screening model, the output of the model is the backup drone with the first ranking, and the backup drone with the first ranking is used as the optimal backup drone to replace the target drone.

10. A geographic information dynamic early warning and control method according to claim 9, characterized in that: In step S4, the geographic information data transmitted by the backup UAV is subjected to stability analysis, and the accuracy of the backup UAV screening model is verified according to the analysis results, as follows: Step B1, obtaining geographic information data transmitted by the backup UAV, for each geographic information data point p, calculating the distance between the geographic information data point p and other data points in the geographic information data set, and obtaining the H nearest neighboring points to the geographic information data point p; Step B2, for geographic information data point p, calculate the average reachable distance to its h nearest neighboring points, and calculate the local reachable density of geographic information data point p; Step B3, calculate the local outlier factor, count the number of times the local outlier factor is greater than the local outlier factor threshold, compare the number of times the local outlier factor is greater than the local outlier factor threshold with the number threshold, verify the accuracy of the backup UAV screening model, if the number of times the local outlier factor is greater than the local outlier factor threshold is greater than the number threshold, then generate an accuracy abnormality signal; if the number of times the local outlier factor is greater than the local outlier factor threshold is less than or equal to the number threshold, then generate an accuracy stability signal.

Images